An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Cerbos to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage complex access policies through simple conversation with your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Cerbos.

  1. 01

    Get server info

    This capability retrieves the specific version and build details of your Cerbos instance.

  2. 02

    Authzen evaluations

    This capability performs batch evaluations of multiple access requests using AuthZEN semantics like deny on first deny.

  3. 03

    Get authzen config

    This capability returns the necessary endpoint URLs for your AuthZEN APIs.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Cerbos.

  1. 04

    Authzen evaluation

    This capability executes a single action evaluation using the AuthZEN entity model.

  2. 05

    Check resources

    This capability provides a read-only evaluation to check if a principal has permissions for a set of resources.

  3. 06

    Plan resources

    This capability produces an AST-based query plan to help you filter resources a principal is allowed to access.

Real work

What teams actually run

01

Policy Debugging

An engineer tests a new RBAC rule by asking the agent to verify access for a specific test user.

02

Data Filtering

A developer generates a query plan to ensure a user only sees resources they are permitted to access.

03

Security Auditing

An auditor runs batch AuthZEN evaluations to confirm permission consistency across the system.

04

System Health Checks

A DevOps engineer checks the current Cerbos build version and configuration endpoints.

Automate a task

Put Cerbos to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Cerbos works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Cerbos to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

970ms average. Fast in production.

Cerbos is checked daily against the live service.

Daily averagePeak 1279ms
Oct 3Today
Fastest day
779ms
Slowest day
1279ms
14-day trend
Slowing+21%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Cerbos, so you can see the experience inside your AI.

It does not authenticate your account with Cerbos. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Cerbos Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Cerbos capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "cerbos-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Cerbos in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Cerbos owners hand off.

This MCP is built for technical teams managing decoupled authorization logic.

  • 01

    Software Engineers

    They use the agent to debug RBAC and ABAC policies without manual API calls.

  • 02

    Security Auditors

    They verify permission logic across various roles and resource attributes.

  • 03

    DevOps Teams

    They monitor Cerbos instance health and configuration metadata.

FAQ

Questions Cerbos owners ask.

  • 01

    How do I connect my Cerbos instance?

    You just need to provide your Cerbos instance base URL, such as http://localhost:3592, when you subscribe to the MCP.

  • 02

    Can I use this with my existing database queries?

    Yes, you can use the plan_resources capability to generate an AST-based query plan that you can apply to your database filters.

  • 03

    What kind of authorization models does this support?

    The MCP works with your existing Cerbos policies, including RBAC and ABAC models.

  • 04

    Does this work with Claude or Cursor?

    Yes, this MCP works with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 05

    Can I run batch permission checks?

    Yes, the authzen_evaluations capability allows for batch evaluation of multiple access requests.

  • 06

    Can I check if a specific user has permission to access a resource?

    Yes. Use the check_resources capability by providing the principal (user) details and the resource information. The agent will return an evaluation of allowed or denied actions.

  • 07

    How do I generate a filter for my database based on user permissions?

    Use the plan_resources capability. It produces a query plan (AST) that you can use to construct database queries, ensuring users only see records they are authorized to access.

  • 08

    Is it possible to verify the Cerbos server version via AI?

    Yes, the get_server_info capability retrieves the version, build date, and commit hash of your connected Cerbos instance.

Explore

More in Developer Tools

Suggestions

Connect Cerbos to Claude, Cursor, ChatGPT & more